Physical Sciences and Mathematics Commons^™

An Evolutionary Perspective On Foraging Strategies And Group Dynamics In Bio-Social Inspired Cognitive Radio Networks, Anna Wisniewska

Dissertations, Theses, and Capstone Projects

Saturation of wireless channels is inevitable as the number of wireless devices grows exponentially in an environment of limited radio spectrum capacity. Cognitive radio technology has been proposed to relieve overcrowded spectrum resources by allowing licensed channels to be opportunistically accessed by unlicensed users (cognitive radio devices) during periods of time when the license holder (primary user) is absent from its channel. Uncoordinated competition over limited resources among cognitive radio devices poses complex co-existence challenges. We propose novel bio-social inspired behavioral models and map out plausible evolutionary trajectories of co-use strategies in the cognitive radio ecosystem. By drawing parallels between …

Semi-Supervised Regression With Generative Adversarial Networks Using Minimal Labeled Data, Greg Olmschenk

Dissertations, Theses, and Capstone Projects

This work studies the generalization of semi-supervised generative adversarial networks (GANs) to regression tasks. A novel feature layer contrasting optimization function, in conjunction with a feature matching optimization, allows the adversarial network to learn from unannotated data and thereby reduce the number of labels required to train a predictive network. An analysis of simulated training conditions is performed to explore the capabilities and limitations of the method. In concert with the semi-supervised regression GANs, an improved label topology and upsampling technique for multi-target regression tasks are shown to reduce data requirements. Improvements are demonstrated on a wide variety of vision …

Do It Like A Syntactician: Using Binary Gramaticality Judgements To Train Sentence Encoders And Assess Their Sensitivity To Syntactic Structure, Pablo Gonzalez Martinez

Dissertations, Theses, and Capstone Projects

The binary nature of grammaticality judgments and their use to access the structure of syntax are a staple of modern linguistics. However, computational models of natural language rarely make use of grammaticality in their training or application. Furthermore, developments in modern neural NLP have produced a myriad of methods that push the baselines in many complex tasks, but those methods are typically not evaluated from a linguistic perspective. In this dissertation I use grammaticality judgements with artificially generated ungrammatical sentences to assess the performance of several neural encoders and propose them as a suitable training target to make models learn …

Online Learning And Planning For Crowd-Aware Service Robot Navigation, Anoop Aroor

Dissertations, Theses, and Capstone Projects

Mobile service robots are increasingly used in indoor environments (e.g., shopping malls or museums) among large crowds of people. To efficiently navigate in these environments, such a robot should be able to exhibit a variety of behaviors. It should avoid crowded areas, and not oppose the flow of the crowd. It should be able to identify and avoid specific crowds that result in additional delays (e.g., children in a particular area might slow down the robot). and to seek out a crowd if its task requires it to interact with as many people as possible. These behaviors require the ability …

Analysis Of A Group Of Automorphisms Of A Free Group As A Platform For Conjugacy-Based Group Cryptography, Pavel Shostak

Dissertations, Theses, and Capstone Projects

Let F be a finitely generated free group and Aut(F) its group of automorphisms.

In this monograph we discuss potential uses of Aut(F) in group-based cryptography.

Our main focus is on using Aut(F) as a platform group for the Anshel-Anshel-Goldfeld protocol, Ko-Lee protocol, and other protocols based on different versions of the conjugacy search problem or decomposition problem, such as Shpilrain-Ushakov protocol.

We attack the Anshel-Anshel-Goldfeld and Ko-Lee protocols by adapting the existing types of the length-based attack to the specifics of Aut(F). We also present our own version of the length-based attack that significantly increases the attack' success …

A Mobile Cyber-Physical System Framework For Aiding People With Visual Impairment, Martin Goldberg

Dissertations, Theses, and Capstone Projects

It is a challenging problem for researchers and engineers in the assistive technology (AT) community to provide suitable solutions for visually impaired people (VIPs) through AT to meet orientation, navigation and mobility (ONM) needs. Given the spectrum of assistive technologies currently available for the purposes of aiding VIPs with ONM, our literature review and survey have shown that there is a reluctance to adopt these technological solutions in the VIP community.

Motivated by these findings, we think it critical to re-examine and rethink the approaches that have been taken. It is our belief that we need to take a different …

Culture Clubs: Processing Speech By Deriving And Exploiting Linguistic Subcultures, David Guy Brizan

Dissertations, Theses, and Capstone Projects

Spoken language understanding systems are error-prone for several reasons, including individual speech variability. This is manifested in many ways, among which are differences in pronunciation, lexical inventory, grammar and disfluencies. There is, however, a lot of evidence pointing to stable language usage within subgroups of a language population. We call these subgroups linguistic subcultures.

The two broad problems are defined and a survey of the work in this space is performed. The two broad problems are: linguistic subculture detection, commonly performed via Language Identification, Accent Identification or Dialect Identification approaches; and speech and language processing tasks taken which may see …

Deep Learning Based Medical Image Analysis With Limited Data, Jiaxing Tan

Dissertations, Theses, and Capstone Projects

Deep Learning Methods have shown its great effort in the area of Computer Vision. However, when solving the problems of medical imaging, deep learning’s power is confined by limited data available. We present a series of novel methodologies for solving medical imaging analysis problems with limited Computed tomography (CT) scans available. Our method, based on deep learning, with different strategies, including using Generative Adversar- ial Networks, two-stage training, infusing the expert knowledge, voting based or converting to other space, solves the data set limitation issue for the cur- rent medical imaging problems, specifically cancer detection and diagnosis, and shows very …